Job Summary: We are seeking a Knowledge Base / Knowledge Graph Engineer for a global banking project focused on building a corporate knowledge platform, evolving towards semantic search and GenAI. Key Highlights: 1. Global project at an international bank 2. Construction of Knowledge Base and Knowledge Graph 3. Evolution towards semantic search, RAG, and LLMs **Knowledge Base / Knowledge Graph Engineer** --------------------------------------------- Madrid, Spain – Project at a major international bank. Full-time **About the Project** --------------------- We are looking for technical profiles to join a **global project of a major international bank focused on building a corporate Knowledge Base**, evolving towards **Knowledge Graph**, advanced **semantic search** capabilities, and potential integration with **RAG and GenAI**. The project’s objective is to build a platform enabling **organization, structuring, indexing, and exploitation of corporate knowledge**, facilitating access via APIs, search engines, and intelligent systems. We seek candidates with experience in **knowledge architecture, information processing, semantic search, or data integration**, who can collaborate in defining and evolving this platform. It is not required to meet all criteria; candidates with partial experience in any of these domains may also be a good fit. **Key Responsibilities** --------------------------------- * Design and build **corporate Knowledge Bases**, including content modeling, basic governance, quality control, and versioning. * Define and manage **Information Architecture**, including: + taxonomies + metadata + categorization + publishing rules * Participate in building **Knowledge Graphs**, including: + entity and relationship modeling + ontologies and controlled vocabularies + mapping across information sources * Define solution architecture: + data ingestion + storage + indexing + search + consumption via APIs * Implement best practices for **data ingestion and integration**, including: + parsing + normalization + deduplication * Collaborate on evolution towards **semantic search, RAG, and LLM-based systems**. **Requirements** -------------- Experience in at least some of the following domains: Knowledge Architecture * Design of **enterprise Knowledge Base** * Content modeling * Information governance * Information architecture Data / Integration Architecture * Data ingestion and processing * Integration of multiple knowledge repositories * Data pipeline design Technologies * **Python** (pipelines, ETL, text processing, APIs) * **Cloud** (preferably AWS) * Integration with repositories such as: + Confluence + SharePoint + ServiceNow + Zendesk * REST APIs Search * Concepts of **indexing and relevance** * Experience with **Elastic / OpenSearch** (desirable) **Nice to Have** ---------------- Knowledge Graph * End\-to\-end implementation of **Knowledge Graph** * Ontologies (RDF, OWL) * Semantic modeling * Basic reasoning Search and GenAI * **Semantic search** * **RAG architectures** * chunking * embeddings * hybrid retrieval * relevance and grounding evaluation Additional Technologies * Graph databases: + Neo4j + Amazon Neptune + Stardog * Vector databases: + Pinecone + Weaviate + FAISS + ChromaDB * LLM frameworks: + LangChain + LlamaIndex * Semantic querying: + SPARQL + GraphQL **We Also Value** --------------------- * Experience in **regulated environments** (PII, access control, auditing). * Experience in **Content Operations / Knowledge\-Centered Service (KCS)**. * Experience in **search engine optimization**: + relevance tuning + synonyms + boosting + query log analysis **What We Are Looking For** ---------------- * Analytical and structured profile. * Ability to work with **architecture, data, AI, and product teams**. * Interest in **knowledge platforms and intelligent systems**. * Experience working in **complex and scalable technical environments**.